© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 23107
    Prev
    Next
    INDEX
    Explanations

    file paths and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    printStackTrace
    0.42
     BufferedReader
    0.41
    extend
    0.39
    escape
    0.39
     NPR
    0.38
     Bucks
    0.38
    <sup>
    0.36
     Fol
    0.35
     Colgate
    0.35
     Coal
    0.35
    POSITIVE LOGITS
    文件
    0.45
    렇
    0.45
     ductile
    0.44
     этот
    0.41
    РИ
    0.41
     molten
    0.40
    utiérrez
    0.40
    বিত্র
    0.39
    ніка
    0.39
     অবহিত
    0.39
    Activations Density 0.001%

    No Known Activations